Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Antoine
    -0.07
    ably
    -0.07
    ующие
    -0.07
    aginator
    -0.07
     Comics
    -0.06
    脂
    -0.06
     island
    -0.06
    _PTR
    -0.06
    (datos
    -0.06
     tip
    -0.06
    POSITIVE LOGITS
     jó
    0.06
    gregated
    0.06
    	a
    0.06
    rientation
    0.06
    nl
    0.06
    four
    0.06
     Sort
    0.06
    	delay
    0.06
                                        ↵
    0.06
     sağlay
    0.06
    Act Density 0.021%

    No Known Activations